INDEX

Explanations

dates and time references

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ãĤ±ãĥĥãĥĪ

-0.17

uyo

-0.14

coe

-0.14

udiant

-0.14

ummings

-0.14

/hash

-0.13

æĭħå½ĵ

-0.13

ENSE

-0.13

sen

-0.13

POSITIVE LOGITS

ady

0.15

arez

0.14

onaut

0.14

semicolon

0.14

adir

0.14

chw

0.13

sole

0.13

alama

0.13

ulis

0.13

ucc

0.13

Activations Density 0.037%

dates and time references

No Comments

No Known Activations